© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 93656
    Prev
    Next
    INDEX
    Explanations

    numerical values and special characters often associated with coding or technical content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Special characters or formatting elements that appear in technical content such as file paths, code, URLs, or mathematical notations.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bos
    -0.07
    ãĥ³ãĥĨãĤ£
    -0.07
    yll
    -0.07
    LÄ°
    -0.07
    ÅĻez
    -0.06
    YRO
    -0.06
     Thoughts
    -0.06
    dub
    -0.06
    کارÛĮ
    -0.06
     "//
    -0.06
    POSITIVE LOGITS
    415
    0.06
    cak
    0.06
    vida
    0.05
    ssue
    0.05
     Hyde
    0.05
    STD
    0.05
     Assertion
    0.05
    711
    0.05
    avers
    0.05
    131
    0.05
    Activations Density 0.067%

    No Known Activations